© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172458
    Prev
    Next
    INDEX
    Explanations

    rubber spring nib

    np_acts-logits-general · gemini-2.5-flash-lite

    Create representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    μένο
    0.52
    혜
    0.48
    μένες
    0.47
    U
    0.47
    apun
    0.45
    는
    0.44
    일
    0.43
    HEY
    0.43
    мол
    0.43
    dehyde
    0.42
    POSITIVE LOGITS
    禣
    0.58
     attributing
    0.49
    trials
    0.44
     Herpes
    0.44
    态度
    0.42
     Erfolg
    0.42
     SULF
    0.42
    ൃശ
    0.42
    ப்பூ
    0.42
     Anfang
    0.42
    Activations Density 0.000%

    No Known Activations